ICPR2020 Paper Browser

Paper download is intended for registered attendees only, and is subjected to the IEEE Copyright Policy. Any other use is strongly forbidden.

Learning to Prune in Training via Dynamic Channel Propagation

Shibo Shen, Rongpeng Li, Zhifeng Zhao, Honggang Zhang, Yugeng Zhou

Auto-TLDR; Dynamic Channel Propagation for Neural Network Pruning

Abstract Slides Poster

In this paper, we propose a novel network training mechanism called "dynamic channel propagation" to prune the model during the training period. In particular, we pick up a specific group of channels in each convolutional layer to participate in the forward propagation in training time according to the significance level of channel, which is defined as channel utility. The utility values with respect to all selected channels are updated simultaneously with the error back-propagation process and will constantly change. Furthermore, when the training ends, channels with high utility values are retained whereas those with low utility values are discarded. Hence, our proposed method trains and prunes neural networks simultaneously. We empirically evaluate our novel training method on various representative benchmark datasets and advanced convolutional neural network (CNN) architectures, including VGGNet and ResNet. The experiment results verify superior performance and robust effectiveness of our approach.

Similar papers

Softer Pruning, Incremental Regularization

Linhang Cai, Zhulin An, Yongjun Xu

Auto-TLDR; Asymptotic SofteR Filter Pruning for Deep Neural Network Pruning

Abstract Slides Poster Similar

Network pruning is widely used to compress Deep Neural Networks (DNNs). The Soft Filter Pruning (SFP) method zeroizes the pruned filters during training while updating them in the next training epoch. Thus the trained information of the pruned filters is completely dropped. To utilize the trained pruned filters, we proposed a SofteR Filter Pruning (SRFP) method and its variant, Asymptotic SofteR Filter Pruning (ASRFP), simply decaying the pruned weights with a monotonic decreasing parameter. Our methods perform well across various netowrks, datasets and pruning rates, also transferable to weight pruning. On ILSVRC-2012, ASRFP prunes 40% of the parameters on ResNet-34 with 1.63% top-1 and 0.68% top-5 accuracy improvement. In theory, SRFP and ASRFP are an incremental regularization of the pruned filters. Besides, We note that SRFP and ASRFP pursue better results while slowing down the speed of convergence.

HFP: Hardware-Aware Filter Pruning for Deep Convolutional Neural Networks Acceleration

Fang Yu, Chuanqi Han, Pengcheng Wang, Ruoran Huang, Xi Huang, Li Cui

Auto-TLDR; Hardware-Aware Filter Pruning for Convolutional Neural Networks

Abstract Slides Poster Similar

Convolutional Neural Networks (CNNs) are powerful but computationally demanding and memory intensive, thus impeding their practical applications on resource-constrained hardware. Filter pruning is an efficient approach for deep CNN compression and acceleration, which aims to eliminate some filters with tolerable performance degradation. In the literature, the majority of approaches prune networks by defining the redundant filters or training the networks with a sparsity prior loss function. These approaches mainly use FLOPs as their speed metric. However, the inference latency of pruned networks cannot be directly controlled on the hardware platform, which is an important dimension of practicality. To address this issue, we propose a novel Hardware-aware Filter Pruning method (HFP) which can produce pruned networks that satisfy the actual latency budget on the hardwares of interest. In addition, we propose an iterative pruning framework called Opti-Cut to decrease the accuracy degradation of pruning process and accelerate the pruning procedure whilst meeting the hardware budget. More specifically, HFP first builds up a lookup table for fast estimating the latency of target network about filter configuration layer by layer. Then, HFP leverages information gain (IG) to globally evaluate the filters' contribution to network output distribution. HFP utilizes the Opti-Cut framework to globally prune filters with the minimum IG one by one until the latency budget is satisfied. We verify the effectiveness of the proposed method on CIFAR-10 and ImageNet. Compared with the state-of-the-art pruning methods, HFP demonstrates superior performances on VGGNet, ResNet and MobileNet V1/V2.

Filter Pruning Using Hierarchical Group Sparse Regularization for Deep Convolutional Neural Networks

Kakeru Mitsuno, Takio Kurita

Auto-TLDR; Hierarchical Group Sparse Regularization for Sparse Convolutional Neural Networks

Abstract Slides Poster Similar

Since the convolutional neural networks are often trained with redundant parameters, it is possible to reduce redundant kernels or filters to obtain a compact network without dropping the classification accuracy. In this paper, we propose a filter pruning method using the hierarchical group sparse regularization. It is shown in our previous work that the hierarchical group sparse regularization is effective in obtaining sparse networks in which filters connected to unnecessary channels are automatically close to zero. After training the convolutional neural network with the hierarchical group sparse regularization, the unnecessary filters are selected based on the increase of the classification loss of the randomly selected training samples to obtain a compact network. It is shown that the proposed method can reduce more than 50% parameters of ResNet for CIFAR-10 with only 0.3% decrease in the accuracy of test samples. Also, 34% parameters of ResNet are reduced for TinyImageNet-200 with higher accuracy than the baseline network.

Progressive Gradient Pruning for Classification, Detection and Domain Adaptation

Le Thanh Nguyen-Meidine, Eric Granger, Marco Pedersoli, Madhu Kiran, Louis-Antoine Blais-Morin

Auto-TLDR; Progressive Gradient Pruning for Iterative Filter Pruning of Convolutional Neural Networks

Abstract Slides Poster Similar

Although deep neural networks (NNs) have achieved state-of-the-art accuracy in many visual recognition tasks, the growing computational complexity and energy consumption of networks remains an issue, especially for applications on plat-forms with limited resources and requiring real-time processing.Filter pruning techniques have recently shown promising results for the compression and acceleration of convolutional NNs(CNNs). However, these techniques involve numerous steps and complex optimisations because some only prune after training CNNs, while others prune from scratch during training by integrating sparsity constraints or modifying the loss function.In this paper we propose a new Progressive Gradient Pruning(PGP) technique for iterative filter pruning during training. In contrast to previous progressive pruning techniques, it relies on a novel filter selection criterion that measures the change in filter weights, uses a new hard and soft pruning strategy and effectively adapts momentum tensors during the backward propagation pass. Experimental results obtained after training various CNNs on image data for classification, object detection and domain adaptation benchmarks indicate that the PGP technique can achieve a better trade-off between classification accuracy and network (time and memory) complexity than PSFP and other state-of-the-art filter pruning techniques.

A Discriminant Information Approach to Deep Neural Network Pruning

Zejiang Hou, Sy Kung

Auto-TLDR; Channel Pruning Using Discriminant Information and Reinforcement Learning

Abstract Slides Poster Similar

Network pruning has become the de facto tool to accelerate and compress deep convolutional neural networks for mobile and edge applications. Previous works tend to perform channel selection in layer-wise manner based on predefined heuristics, without considering layer importance or systematically optimizing the pruned structure. In this work, we propose a novel channel pruning method that jointly harnesses two strategies: (1) a channel importance ranking heuristics based on the feature-maps discriminant power, (2) a searching method for optimal pruning budget allocation. For the former, we propose a Discriminant Information (DI) based channel selection algorithm. We use a small batch of training samples to compute the DI score for each channel and rank the channel importance so that channels really contributing to the feature-maps discriminant power are retained. For the latter, in order to search the optimal pruning budget allocation, we formulate a reward maximization problem to discover the layer importance and generating the pruning budget accordingly. Such reward maximization can be efficiently solved by the policy gradient algorithm in reinforcement learning, yielding our final pruned network which achieves the best accuracy-efficiency trade-off. Experiments on a variety of CNN architectures and benchmark datasets show that our proposed channel pruning methods compare favorably with previous state-of-the-art methods. On ImageNet, our pruned MobileNetV2 outperforms the previous layer-wise state-of-the-art pruning method CPLI \cite{guo2020channel} by 2\% Top-1 accuracy while reducing the FLOPs by 50\%.

Slimming ResNet by Slimming Shortcut

Donggyu Joo, Doyeon Kim, Junmo Kim

Auto-TLDR; SSPruning: Slimming Shortcut Pruning on ResNet Based Networks

Abstract Slides Poster Similar

Conventional network pruning methods on convolutional neural networks (CNNs) reduce the number of input or output channels of convolution layers. With these approaches, the channels in the plain network can be pruned without any restrictions. However, in case of the ResNet based networks which have shortcuts (skip connections), the channel slimming of existing pruning methods is limited to the inside of each residual block. Since the number of Flops and parameters are also highly related to the number of channels in the shortcuts, more investigation on pruning channels in shortcuts is required. In this paper, we propose a novel pruning method, Slimming Shortcut Pruning (SSPruning), for pruning channels in shortcuts on ResNet based networks. First, we separate the long shortcut in individual regions that can be pruned independently without considering its long connections. Then, by applying our Importance Learning Gate (ILG) which learns the importance of channels globally regardless of channel type and location (i.e., in the shortcut or inside of the block), we can finally achieve an optimally pruned model. Through various experiments, we have confirmed that our method yields outstanding results when we prune the shortcuts and inside of the block together.

Activation Density Driven Efficient Pruning in Training

Timothy Foldy-Porto, Yeshwanth Venkatesha, Priyadarshini Panda

Auto-TLDR; Real-Time Neural Network Pruning with Compressed Networks

Abstract Slides Poster Similar

Neural network pruning with suitable retraining can yield networks with considerably fewer parameters than the original with comparable degrees of accuracy. Typical pruning methods require large, fully trained networks as a starting point from which they perform a time-intensive iterative pruning and retraining procedure to regain the original accuracy. We propose a novel pruning method that prunes a network real-time during training, reducing the overall training time to achieve an efficient compressed network. We introduce an activation density based analysis to identify the optimal relative sizing or compression for each layer of the network. Our method is architecture agnostic, allowing it to be employed on a wide variety of systems. For VGG-19 and ResNet18 on CIFAR-10, CIFAR-100, and TinyImageNet, we obtain exceedingly sparse networks (up to $200 \times$ reduction in parameters and over $60 \times$ reduction in inference compute operations in the best case) with accuracy comparable to the baseline network. By reducing the network size periodically during training, we achieve total training times that are shorter than those of previously proposed pruning methods. Furthermore, training compressed networks at different epochs with our proposed method yields considerable reduction in training compute complexity ($1.6\times$ to $3.2\times$ lower) at near iso-accuracy as compared to a baseline network trained entirely from scratch.

Neuron-Based Network Pruning Based on Majority Voting

Ali Alqahtani, Xianghua Xie, Ehab Essa, Mark W. Jones

Auto-TLDR; Large-Scale Neural Network Pruning using Majority Voting

Abstract Slides Poster Similar

The achievement of neural networks in a variety of applications is accompanied by a dramatic increase in computational costs and memory requirements. In this paper, we propose an efficient method to simultaneously identify the critical neurons and prune the model during training without involving any pre-training or fine-tuning procedures. Unlike existing methods, which accomplish this task in a greedy fashion, we propose a majority voting technique to compare the activation values among neurons and assign a voting score to quantitatively evaluate their importance.This mechanism helps to effectively reduce model complexity by eliminating the less influential neurons and aims to determine a subset of the whole model that can represent the reference model with much fewer parameters within the training process. Experimental results show that majority voting efficiently compresses the network with no drop in model accuracy, pruning more than 79\% of the original model parameters on CIFAR10 and more than 91\% of the original parameters on MNIST. Moreover, we show that with our proposed method, sparse models can be further pruned into even smaller models by removing more than 60\% of the parameters, whilst preserving the reference model accuracy.

Exploiting Non-Linear Redundancy for Neural Model Compression

Muhammad Ahmed Shah, Raphael Olivier, Bhiksha Raj

Auto-TLDR; Compressing Deep Neural Networks with Linear Dependency

Abstract Slides Poster Similar

Deploying deep learning models with millions, even billions, of parameters is challenging given real world memory, power and compute constraints. In an effort to make these models more practical, in this paper, we propose a novel model compression approach that exploits linear dependence between the activations in a layer to eliminate entire structural units (neurons/convolutional filters). Our approach also adjusts the weights of the layer in a manner that is provably lossless while training if the removed neuron was perfectly predictable. We combine this approach with an annealing algorithm that may be applied during training, or even on a trained model, and demonstrate, using popular datasets, that our technique can reduce the parameters of VGG and AlexNet by more than 97\% on \cifar, 85\% on \caltech, and 19\% on ImageNet at less than 2\% loss in accuracy. Furthermore, we provide theoretical results showing that in overparametrized, locally linear (ReLU) neural networks where redundant features exist, and with correct hyperparameter selection, our method is indeed able to capture and suppress those dependencies.

On the Information of Feature Maps and Pruning of Deep Neural Networks

Mohammadreza Soltani, Suya Wu, Jie Ding, Robert Ravier, Vahid Tarokh

Auto-TLDR; Compressing Deep Neural Models Using Mutual Information

Abstract Slides Poster Similar

A technique for compressing deep neural models achieving competitive performance to state-of-the-art methods is proposed. The approach utilizes the mutual information between the feature maps and the output of the model in order to prune the redundant layers of the network. Extensive numerical experiments on both CIFAR-10, CIFAR-100, and Tiny ImageNet data sets demonstrate that the proposed method can be effective in compressing deep models, both in terms of the numbers of parameters and operations. For instance, by applying the proposed approach to DenseNet model with 0.77 million parameters and 293 million operations for classification of CIFAR-10 data set, a reduction of 62.66% and 41.00% in the number of parameters and the number of operations are respectively achieved, while increasing the test error only by less than 1%.

Compression of YOLOv3 Via Block-Wise and Channel-Wise Pruning for Real-Time and Complicated Autonomous Driving Environment Sensing Applications

Jiaqi Li, Yanan Zhao, Li Gao, Feng Cui

Auto-TLDR; Pruning YOLOv3 with Batch Normalization for Autonomous Driving

Abstract Slides Poster Similar

Nowadays, in the area of autonomous driving, the computational power of the object detectors is limited by the embedded devices and the public datasets for autonomous driving are over-idealistic. In this paper, we propose a pipeline combining both block-wise pruning and channel-wise pruning to compress the object detection model iteratively. We enforce the introduced factor of the residual blocks and the scale parameters in Batch Normalization (BN) layers to sparsity to select the less important residual blocks and channels. Moreover, a modified loss function has been proposed to remedy the class-imbalance problem. After removing the unimportant structures iteratively, we get the pruned YOLOv3 trained on our datasets which have more abundant and elaborate classes. Evaluated by our validation sets on the server, the pruned YOLOv3 saves 79.7% floating point operations (FLOPs), 93.8% parameter size, 93.8% model volume and 45.4% inference times with only 4.16% mean of average precision (mAP) loss. Evaluated on the embedded device, the pruned model operates about 13 frames per second with 4.53% mAP loss. These results show that the real-time property and accuracy of the pruned YOLOv3 can meet the needs of the embedded devices in complicated autonomous driving environments.

Channel Planting for Deep Neural Networks Using Knowledge Distillation

Kakeru Mitsuno, Yuichiro Nomura, Takio Kurita

Auto-TLDR; Incremental Training for Deep Neural Networks with Knowledge Distillation

Abstract Slides Poster Similar

In recent years, deeper and wider neural networks have shown excellent performance in computer vision tasks, while their enormous amount of parameters results in increased computational cost and overfitting. Several methods have been proposed to compress the size of the networks without reducing network performance. Network pruning can reduce redundant and unnecessary parameters from a network. Knowledge distillation can transfer the knowledge of deeper and wider networks to smaller networks. The performance of the smaller network obtained by these methods is bounded by the predefined network. Neural architecture search has been proposed, which can search automatically the architecture of the networks to break the structure limitation. Also, there is a dynamic configuration method to train networks incrementally as sub-networks. In this paper, we present a novel incremental training algorithm for deep neural networks called planting. Our planting can search the optimal network architecture with smaller number of parameters for improving the network performance by augmenting channels incrementally to layers of the initial networks while keeping the earlier trained parameters fixed. Also, we propose using the knowledge distillation method for training the channels planted. By transferring the knowledge of deeper and wider networks, we can grow the networks effectively and efficiently. We evaluate the effectiveness of the proposed method on different datasets such as CIFAR-10/100 and STL-10. For the STL-10 dataset, we show that we are able to achieve comparable performance with only 7% parameters compared to the larger network and reduce the overfitting caused by a small amount of the data.

Speeding-Up Pruning for Artificial Neural Networks: Introducing Accelerated Iterative Magnitude Pruning

Marco Zullich, Eric Medvet, Felice Andrea Pellegrino, Alessio Ansuini

Auto-TLDR; Iterative Pruning of Artificial Neural Networks with Overparametrization

Abstract Slides Poster Similar

In recent years, Artificial Neural Networks (ANNs) pruning has become the focal point of many researches, due to the extreme overparametrization of such models. This has urged the scientific world to investigate methods for the simplification of the structure of weights in ANNs, mainly in an effort to reduce time for both training and inference. Frankle and Carbin and later Renda, Frankle, and Carbin introduced and refined an iterative pruning method which is able to effectively prune the network of a great portion of its parameters with little to no loss in performance. On the downside, this method requires a large amount of time for its application, since, for each iteration, the network has to be trained for (almost) the same amount of epochs of the unpruned network. In this work, we show that, for a limited setting, if targeting high overall sparsity rates, this time can be effectively reduced for each iteration, save for the last one, by more than 50%, while yielding a final product (i.e., final pruned network) whose performance is comparable to the ANN obtained using the existing method.

Learning Sparse Deep Neural Networks Using Efficient Structured Projections on Convex Constraints for Green AI

Michel Barlaud, Frederic Guyard

Auto-TLDR; Constrained Deep Neural Network with Constrained Splitting Projection

Abstract Slides Poster Similar

In recent years, deep neural networks (DNN) have been applied to different domains and achieved dramatic performance improvements over state-of-the-art classical methods. These performances of DNNs were however often obtained with networks containing millions of parameters and which training required heavy computational power. In order to cope with this computational issue a huge literature deals with proximal regularization methods which are time consuming.\\ In this paper, we propose instead a constrained approach. We provide the general framework for our new splitting projection gradient method. Our splitting algorithm iterates a gradient step and a projection on convex sets. We study algorithms for different constraints: the classical $\ell_1$ unstructured constraint and structured constraints such as the nuclear norm, the $\ell_{2,1} $ constraint (Group LASSO). We propose a new $\ell_{1,1} $ structured constraint for which we provide a new projection algorithm We demonstrate the effectiveness of our method on three popular datasets (MNIST, Fashion MNIST and CIFAR). Experiments on these datasets show that our splitting projection method with our new $\ell_{1,1} $ structured constraint provides the best reduction of memory and computational power. Experiments show that fully connected linear DNN are more efficient for green AI.

Dynamic Multi-Path Neural Network

Yingcheng Su, Yichao Wu, Ken Chen, Ding Liang, Xiaolin Hu

Auto-TLDR; Dynamic Multi-path Neural Network

Abstract Slides Similar

Although deeper and larger neural networks have achieved better performance, due to overwhelming burden on computation, they cannot meet the demands of deployment on resource-limited devices. An effective strategy to address this problem is to make use of dynamic inference mechanism, which changes the inference path for different samples at runtime. Existing methods only reduce the depth by skipping an entire specific layer, which may lose important information in this layer. In this paper, we propose a novel method called Dynamic Multi-path Neural Network (DMNN), which provides more topology choices in terms of both width and depth on the fly. For better modelling the inference path selection, we further introduce previous state and object category information to guide the training process. Compared to previous dynamic inference techniques, the proposed method is more flexible and easier to incorporate into most modern network architectures. Experimental results on ImageNet and CIFAR-100 demonstrate the superiority of our method on both efficiency and classification accuracy.

Attention Based Pruning for Shift Networks

Ghouthi Hacene, Carlos Lassance, Vincent Gripon, Matthieu Courbariaux, Yoshua Bengio

Auto-TLDR; Shift Attention Layers for Efficient Convolutional Layers

Abstract Slides Poster Similar

In many application domains such as computer vision, Convolutional Layers (CLs) are key to the accuracy of deep learning methods. However, it is often required to assemble a large number of CLs, each containing thousands of parameters, in order to reach state-of-the-art accuracy, thus resulting in complex and demanding systems that are poorly fitted to resource-limited devices. Recently, methods have been proposed to replace the generic convolution operator by the combination of a shift operation and a simpler 1x1 convolution. The resulting block, called Shift Layer (SL), is an efficient alternative to CLs in the sense it allows to reach similar accuracies on various tasks with faster computations and fewer parameters. In this contribution, we introduce Shift Attention Layers (SALs), which extend SLs by using an attention mechanism that learns which shifts are the best at the same time the network function is trained. We demonstrate SALs are able to outperform vanilla SLs (and CLs) on various object recognition benchmarks while significantly reducing the number of float operations and parameters for the inference.

MINT: Deep Network Compression Via Mutual Information-Based Neuron Trimming

Madan Ravi Ganesh, Jason Corso, Salimeh Yasaei Sekeh

Auto-TLDR; Mutual Information-based Neuron Trimming for Deep Compression via Pruning

Abstract Slides Poster Similar

Most approaches to deep neural network compression via pruning either evaluate a filter’s importance using its weights or optimize an alternative objective function with sparsity constraints. While these methods offer a useful way to approximate contributions from similar filters, they often either ignore the dependency between layers or solve a more difficult optimization objective than standard cross-entropy. Our method, Mutual Information-based Neuron Trimming (MINT), approaches deep compression via pruning by enforcing sparsity based on the strength of the relationship between filters of adjacent layers, across every pair of layers. The relationship is calculated using conditional geometric mutual information which evaluates the amount of similar information exchanged between the filters using a graph-based criterion. When pruning a network, we ensure that retained filters contribute the majority of the information towards succeeding layers which ensures high performance. Our novel approach outperforms existing state-of-the-art compression-via-pruning methods on the standard benchmarks for this task: MNIST, CIFAR-10, and ILSVRC2012, across a variety of network architectures. In addition, we discuss our observations of a common denominator between our pruning methodology’s response to adversarial attacks and calibration statistics when compared to the original network.

Exploiting Elasticity in Tensor Ranks for Compressing Neural Networks

Jie Ran, Rui Lin, Hayden Kwok-Hay So, Graziano Chesi, Ngai Wong

Auto-TLDR; Nuclear-Norm Rank Minimization Factorization for Deep Neural Networks

Abstract Slides Poster Similar

Elasticities in depth, width, kernel size and resolution have been explored in compressing deep neural networks (DNNs). Recognizing that the kernels in a convolutional neural network (CNN) are 4-way tensors, we further exploit a new elasticity dimension along the input-output channels. Specifically, a novel nuclear-norm rank minimization factorization (NRMF) approach is proposed to dynamically and globally search for the reduced tensor ranks during training. Correlation between tensor ranks across multiple layers is revealed, and a graceful tradeoff between model size and accuracy is obtained. Experiments then show the superiority of NRMF over the previous non-elastic variational Bayesian matrix factorization (VBMF) scheme.

Compact CNN Structure Learning by Knowledge Distillation

Waqar Ahmed, Andrea Zunino, Pietro Morerio, Vittorio Murino

Auto-TLDR; Knowledge Distillation for Compressing Deep Convolutional Neural Networks

Abstract Slides Poster Similar

The concept of compressing deep Convolutional Neural Networks (CNNs) is essential to use limited computation, power, and memory resources on embedded devices. However, existing methods achieve this objective at the cost of a drop in inference accuracy in computer vision tasks. To address such a drawback, we propose a framework that leverages knowledge distillation along with customizable block-wise optimization to learn a lightweight CNN structure while preserving better control over the compression-performance tradeoff. Considering specific resource constraints, e.g., floating-point operations per second (FLOPs) or model-parameters, our method results in a state of the art network compression while being capable of achieving better inference accuracy. In a comprehensive evaluation, we demonstrate that our method is effective, robust, and consistent with results over a variety of network architectures and datasets, at negligible training overhead. In particular, for the already compact network MobileNet_v2, our method offers up to 2x and 5.2x better model compression in terms of FLOPs and model-parameters, respectively, while getting 1.05% better model performance than the baseline network.

E-DNAS: Differentiable Neural Architecture Search for Embedded Systems

Javier García López, Antonio Agudo, Francesc Moreno-Noguer

Auto-TLDR; E-DNAS: Differentiable Architecture Search for Light-Weight Networks for Image Classification

Abstract Slides Poster Similar

Designing optimal and light weight networks to fit in resource-limited platforms like mobiles, DSPs or GPUs is a challenging problem with a wide range of interesting applications, {\em e.g.} in embedded systems for autonomous driving. While most approaches are based on manual hyperparameter tuning, there exist a new line of research, the so-called NAS (Neural Architecture Search) methods, that aim to optimize several metrics during the design process, including memory requirements of the network, number of FLOPs, number of MACs (Multiply-ACcumulate operations) or inference latency. However, while NAS methods have shown very promising results, they are still significantly time and cost consuming. In this work we introduce E-DNAS, a differentiable architecture search method, which improves the efficiency of NAS methods in designing light-weight networks for the task of image classification. Concretely, E-DNAS computes, in a differentiable manner, the optimal size of a number of meta-kernels that capture patterns of the input data at different resolutions. We also leverage on the additive property of convolution operations to merge several kernels with different compatible sizes into a single one, reducing thus the number of operations and the time required to estimate the optimal configuration. We evaluate our approach on several datasets to perform classification. We report results in terms of the SoC (System on Chips) metric, typically used in the Texas Instruments TDA2x families for autonomous driving applications. The results show that our approach allows designing low latency architectures significantly faster than state-of-the-art.

Norm Loss: An Efficient yet Effective Regularization Method for Deep Neural Networks

Theodoros Georgiou, Sebastian Schmitt, Thomas Baeck, Wei Chen, Michael Lew

Auto-TLDR; Weight Soft-Regularization with Oblique Manifold for Convolutional Neural Network Training

Abstract Slides Poster Similar

Convolutional neural network training can suffer from diverse issues like exploding or vanishing gradients, scaling-based weight space symmetry and covariant-shift. In order to address these issues, researchers develop weight regularization methods and activation normalization methods. In this work we propose a weight soft-regularization method based on the Oblique manifold. The proposed method uses a loss function which pushes each weight vector to have a norm close to one, i.e. the weight matrix is smoothly steered toward the so-called Oblique manifold. We evaluate our method on the very popular CIFAR-10, CIFAR-100 and ImageNet 2012 datasets using two state-of-the-art architectures, namely the ResNet and wide-ResNet. Our method introduces negligible computational overhead and the results show that it is competitive to the state-of-the-art and in some cases superior to it. Additionally, the results are less sensitive to hyperparameter settings such as batch size and regularization factor.

How Does DCNN Make Decisions?

Yi Lin, Namin Wang, Xiaoqing Ma, Ziwei Li, Gang Bai

Auto-TLDR; Exploring Deep Convolutional Neural Network's Decision-Making Interpretability

Abstract Slides Poster Similar

Deep Convolutional Neural Networks (DCNN), despite imitating the human visual system, present no such decision credibility as human observers. This phenomenon, therefore, leads to the limitations of DCNN's applications in the security and trusted computing, such as self-driving cars and medical diagnosis. Focusing on this issue, our work aims to explore the way DCNN makes decisions. In this paper, the major contributions we made are: firstly, provide the hypothesis, “point-wise activation” of convolution function, according to the analysis of DCNN’s architectures and training process; secondly, point out the effect of “point-wise activation” on DCNN’s uninterpretable classification and pool robustness, and then suggest, in particular, the contradiction between the traditional and DCNN’s convolution kernel functions; finally, distinguish decision-making interpretability from semantic interpretability, and indicate that DCNN’s decision-making mechanism need to evolve towards the direction of semantics in the future. Besides, the “point-wise activation” hypothesis and conclusions proposed in our paper are supported by extensive experimental results.

VPU Specific CNNs through Neural Architecture Search

Ciarán Donegan, Hamza Yous, Saksham Sinha, Jonathan Byrne

Auto-TLDR; Efficient Convolutional Neural Networks for Edge Devices using Neural Architecture Search

Abstract Slides Poster Similar

The success of deep learning at computer vision tasks has led to an ever-increasing number of applications on edge devices. Often with the use of edge AI hardware accelerators like the Intel Movidius Vision Processing Unit (VPU). Performing computer vision tasks on edge devices is challenging. Many Convolutional Neural Networks (CNNs) are too complex to run on edge devices with limited computing power. This has created large interest in designing efficient CNNs and one promising way of doing this is through Neural Architecture Search (NAS). NAS aims to automate the design of neural networks. NAS can also optimize multiple different objectives together, like accuracy and efficiency, which is difficult for humans. In this paper, we use a differentiable NAS method to find efficient CNNs for VPU that achieves state-of-the-art classification accuracy on ImageNet. Our NAS designed model outperforms MobileNetV2, having almost 1\% higher top-1 accuracy while being 13\% faster on MyriadX VPU. To the best of our knowledge, this is the first time a VPU specific CNN has been designed using a NAS algorithm. Our results also reiterate the fact that efficient networks must be designed for each specific hardware. We show that efficient networks targeted at different devices do not perform as well on the VPU.

Dual-Attention Guided Dropblock Module for Weakly Supervised Object Localization

Junhui Yin, Siqing Zhang, Dongliang Chang, Zhanyu Ma, Jun Guo

Auto-TLDR; Dual-Attention Guided Dropblock for Weakly Supervised Object Localization

Abstract Slides Poster Similar

Attention mechanisms is frequently used to learn the discriminative features for better feature representations. In this paper, we extend the attention mechanism to the task of weakly supervised object localization (WSOL) and propose the dual-attention guided dropblock module (DGDM), which aims at learning the informative and complementary visual patterns for WSOL. This module contains two key components, the channel attention guided dropout (CAGD) and the spatial attention guided dropblock (SAGD). To model channel interdependencies, the CAGD ranks the channel attentions and treats the top-k attentions with the largest magnitudes as the important ones. It also keeps some low-valued elements to increase their value if they become important during training. The SAGD can efficiently remove the most discriminative information by erasing the contiguous regions of feature maps rather than individual pixels. This guides the model to capture the less discriminative parts for classification. Furthermore, it can also distinguish the foreground objects from the background regions to alleviate the attention misdirection. Experimental results demonstrate that the proposed method achieves new state-of-the-art localization performance.

Stage-Wise Neural Architecture Search

Artur Jordão, Fernando Akio Yamada, Maiko Lie, William Schwartz

Auto-TLDR; Efficient Neural Architecture Search for Deep Convolutional Networks

Abstract Slides Poster Similar

Modern convolutional networks such as ResNet and NASNet have achieved state-of-the-art results in many computer vision applications. These architectures consist of stages, which are sets of layers that operate on representations in the same resolution. It has been demonstrated that increasing the number of layers in each stage improves the prediction ability of the network. However, the resulting architecture becomes computationally expensive in terms of floating point operations, memory requirements and inference time. Thus, significant human effort is necessary to evaluate different trade-offs between depth and performance. To handle this problem, recent works have proposed to automatically design high-performance architectures, mainly by means of neural architecture search (NAS). Current NAS strategies analyze a large set of possible candidate architectures and, hence, require vast computational resources and take many GPUs days. Motivated by this, we propose a NAS approach to efficiently design accurate and low-cost convolutional architectures and demonstrate that an efficient strategy for designing these architectures is to learn the depth stage-by-stage. For this purpose, our approach increases depth incrementally in each stage taking into account its importance, such that stages with low importance are kept shallow while stages with high importance become deeper. We conduct experiments on the CIFAR and different versions of ImageNet datasets, where we show that architectures discovered by our approach achieve better accuracy and efficiency than human-designed architectures. Additionally, we show that architectures discovered on CIFAR-10 can be successfully transferred to large datasets. Compared to previous NAS approaches, our method is substantially more efficient, as it evaluates one order of magnitude fewer models and yields architectures on par with the state-of-the-art.

Is the Meta-Learning Idea Able to Improve the Generalization of Deep Neural Networks on the Standard Supervised Learning?

Xiang Deng, Zhongfei Zhang

Auto-TLDR; Meta-learning Based Training of Deep Neural Networks for Few-Shot Learning

Abstract Slides Poster Similar

Substantial efforts have been made on improving the generalization abilities of deep neural networks (DNNs) in order to obtain better performances without introducing more parameters. On the other hand, meta-learning approaches exhibit powerful generalization on new tasks in few-shot learning. Intuitively, few-shot learning is more challenging than the standard supervised learning as each target class only has a very few or no training samples. The natural question that arises is whether the meta-learning idea can be used for improving the generalization of DNNs on the standard supervised learning. In this paper, we propose a novel meta-learning based training procedure (MLTP) for DNNs and demonstrate that the meta-learning idea can indeed improve the generalization abilities of DNNs. MLTP simulates the meta-training process by considering a batch of training samples as a task. The key idea is that the gradient descent step for improving the current task performance should also improve a new task performance, which is ignored by the current standard procedure for training neural networks. MLTP also benefits from all the existing training techniques such as dropout, weight decay, and batch normalization. We evaluate MLTP by training a variety of small and large neural networks on three benchmark datasets, i.e., CIFAR-10, CIFAR-100, and Tiny ImageNet. The experimental results show a consistently improved generalization performance on all the DNNs with different sizes, which verifies the promise of MLTP and demonstrates that the meta-learning idea is indeed able to improve the generalization of DNNs on the standard supervised learning.

Improving Batch Normalization with Skewness Reduction for Deep Neural Networks

Pak Lun Kevin Ding, Martin Sarah, Baoxin Li

Auto-TLDR; Batch Normalization with Skewness Reduction

Abstract Slides Poster Similar

Batch Normalization (BN) is a well-known technique used in training deep neural networks. The main idea behind batch normalization is to normalize the features of the layers ($i.e.$, transforming them to have a mean equal to zero and a variance equal to one). Such a procedure encourages the optimization landscape of the loss function to be smoother, and improve the learning of the networks for both speed and performance. In this paper, we demonstrate that the performance of the network can be improved, if the distributions of the features of the output in the same layer are similar. As normalizing based on mean and variance does not necessarily make the features to have the same distribution, we propose a new normalization scheme: Batch Normalization with Skewness Reduction (BNSR). Comparing with other normalization approaches, BNSR transforms not just only the mean and variance, but also the skewness of the data. By tackling this property of a distribution, we are able to make the output distributions of the layers to be further similar. The nonlinearity of BNSR may further improve the expressiveness of the underlying network. Comparisons with other normalization schemes are tested on the CIFAR-100 and ImageNet datasets. Experimental results show that the proposed approach can outperform other state-of-the-arts that are not equipped with BNSR.

Towards Low-Bit Quantization of Deep Neural Networks with Limited Data

Yong Yuan, Chen Chen, Xiyuan Hu, Silong Peng

Auto-TLDR; Low-Precision Quantization of Deep Neural Networks with Limited Data

Abstract Slides Poster Similar

Recent machine learning methods use increasingly large deep neural networks to achieve state-of-the-art results in various tasks. Network quantization can effectively reduce computation and memory costs without modifying network structures, facilitating the deployment of deep neural networks (DNNs) on cloud and edge devices. However, most of the existing methods usually need time-consuming training or fine-tuning and access to the original training dataset that may be unavailable due to privacy or security concerns. In this paper, we present a novel method to achieve low-precision quantization of deep neural networks with limited data. Firstly, to reduce the complexity of per-channel quantization and the degeneration of per-layer quantization, we introduce group-wise quantization which separates the output channels into groups that each group is quantized separately. Secondly, to better distill knowledge from the pre-trained FP32 model with limited data, we introduce a two-stage knowledge distillation method that divides the optimization process into independent optimization stage and joint optimization stage to address the limitation of layer-wise supervision and global supervision. Extensive experiments on ImageNet2012 (ResNet18/50, ShuffleNetV2, and MobileNetV2) demonstrate that the proposed approach can significantly improve the quantization model's accuracy when only a few training samples are available. We further show that the method also extends to other computer vision architectures and tasks such as object detection and semantic segmentation.

WeightAlign: Normalizing Activations by Weight Alignment

Xiangwei Shi, Yunqiang Li, Xin Liu, Jan Van Gemert

Auto-TLDR; WeightAlign: Normalization of Activations without Sample Statistics

Abstract Slides Poster Similar

Batch normalization (BN) allows training very deep networks by normalizing activations by mini-batch sample statistics which renders BN unstable for small batch sizes. Current small-batch solutions such as Instance Norm, Layer Norm, and Group Norm use channel statistics which can be computed even for a single sample. Such methods are less stable than BN as they critically depend on the statistics of a single input sample. To address this problem, we propose a normalization of activation without sample statistics. We present WeightAlign: a method that normalizes the weights by the mean and scaled standard derivation computed within a filter, which normalizes activations without computing any sample statistics. Our proposed method is independent of batch size and stable over a wide range of batch sizes. Because weight statistics are orthogonal to sample statistics, we can directly combine WeightAlign with any method for activation normalization. We experimentally demonstrate these benefits for classification on CIFAR-10, CIFAR-100, ImageNet, for semantic segmentation on PASCAL VOC 2012 and for domain adaptation on Office-31.

Feature-Dependent Cross-Connections in Multi-Path Neural Networks

Dumindu Tissera, Kasun Vithanage, Rukshan Wijesinghe, Kumara Kahatapitiya, Subha Fernando, Ranga Rodrigo

Auto-TLDR; Multi-path Networks for Adaptive Feature Extraction

Abstract Slides Poster Similar

Learning a particular task from a dataset, samples in which originate from diverse contexts, is challenging, and usually addressed by deepening or widening standard neural networks. As opposed to conventional network widening, multi-path architectures restrict the quadratic increment of complexity to a linear scale. However, existing multi-column/path networks or model ensembling methods do not consider any feature-dependant allocation of parallel resources, and therefore, tend to learn redundant features. Given a layer in a multi-path network, if we restrict each path to learn a context-specific set of features and introduce a mechanism to intelligently allocate incoming feature maps to such paths, each path can specialize in a certain context, reducing the redundancy and improving the quality of extracted features. This eventually leads to better-optimized usage of parallel resources. To do this, we propose inserting feature-dependant cross-connections between parallel sets of feature maps in successive layers. The weights of these cross-connections are learned based on the input features of the particular layer. Our multi-path networks show improved image recognition accuracy at a similar complexity compared to conventional and state-of-the-art methods for deepening, widening and adaptive feature extracting, in both small and large scale datasets.

Improved Residual Networks for Image and Video Recognition

Ionut Cosmin Duta, Li Liu, Fan Zhu, Ling Shao

Auto-TLDR; Residual Networks for Deep Learning

Abstract Slides Poster Similar

Residual networks (ResNets) represent a powerful type of convolutional neural network (CNN) architecture, widely adopted and used in various tasks. In this work we propose an improved version of ResNets. Our proposed improvements address all three main components of a ResNet: the flow of information through the network layers, the residual building block, and the projection shortcut. We are able to show consistent improvements in accuracy and learning convergence over the baseline. For instance, on ImageNet dataset, using the ResNet with 50 layers, for top-1 accuracy we can report a 1.19% improvement over the baseline in one setting and around 2% boost in another. Importantly, these improvements are obtained without increasing the model complexity. Our proposed approach allows us to train extremely deep networks, while the baseline shows severe optimization issues. We report results on three tasks over six datasets: image classification (ImageNet, CIFAR-10 and CIFAR-100), object detection (COCO) and video action recognition (Kinetics-400 and Something-Something-v2). In the deep learning era, we establish a new milestone for the depth of a CNN. We successfully train a 404-layer deep CNN on the ImageNet dataset and a 3002-layer network on CIFAR-10 and CIFAR-100, while the baseline is not able to converge at such extreme depths. Code is available at: https://github.com/iduta/iresnet

MaxDropout: Deep Neural Network Regularization Based on Maximum Output Values

Claudio Filipi Gonçalves Santos, Danilo Colombo, Mateus Roder, Joao Paulo Papa

Auto-TLDR; MaxDropout: A Regularizer for Deep Neural Networks

Abstract Slides Poster Similar

Different techniques have emerged in the deep learning scenario, such as Convolutional Neural Networks, Deep Belief Networks, and Long Short-Term Memory Networks, to cite a few. In lockstep, regularization methods, which aim to prevent overfitting by penalizing the weight connections, or turning off some units, have been widely studied either. In this paper, we present a novel approach called MaxDropout, a regularizer for deep neural network models that works in a supervised fashion by removing (shutting off) the prominent neurons (i.e., most active) in each hidden layer. The model forces fewer activated units to learn more representative information, thus providing sparsity. Regarding the experiments, we show that it is possible to improve existing neural networks and provide better results in neural networks when Dropout is replaced by MaxDropout. The proposed method was evaluated in image classification, achieving comparable results to existing regularizers, such as Cutout and RandomErasing, also improving the accuracy of neural networks that uses Dropout by replacing the existing layer by MaxDropout.

A Close Look at Deep Learning with Small Data

Lorenzo Brigato, Luca Iocchi

Auto-TLDR; Low-Complex Neural Networks for Small Data Conditions

Abstract Slides Poster Similar

In this work, we perform a wide variety of experiments with different Deep Learning architectures in small data conditions. We show that model complexity is a critical factor when only a few samples per class are available. Differently from the literature, we improve the state of the art using low complexity models. We show that standard convolutional neural networks with relatively few parameters are effective in this scenario. In many of our experiments, low complexity models outperform state-of-the-art architectures. Moreover, we propose a novel network that uses an unsupervised loss to regularize its training. Such architecture either improves the results either performs comparably well to low capacity networks. Surprisingly, experiments show that the dynamic data augmentation pipeline is not beneficial in this particular domain. Statically augmenting the dataset might be a promising research direction while dropout maintains its role as a good regularizer.

Probability Guided Maxout

Claudio Ferrari, Stefano Berretti, Alberto Del Bimbo

Auto-TLDR; Probability Guided Maxout for CNN Training

Abstract Slides Poster Similar

In this paper, we propose an original CNN training strategy that brings together ideas from both dropout-like regularization methods and solutions that learn discriminative features. We propose a dropping criterion that, differently from dropout and its variants, is deterministic rather than random. It grounds on the empirical evidence that feature descriptors with larger $L2$-norm and highly-active nodes are strongly correlated to confident class predictions. Thus, our criterion guides towards dropping a percentage of the most active nodes of the descriptors, proportionally to the estimated class probability. We simultaneously train a per-sample scaling factor to balance the expected output across training and inference. This further allows us to keep high the descriptor's L2-norm, which we show enforces confident predictions. The combination of these two strategies resulted in our ``Probability Guided Maxout'' solution that acts as a training regularizer. We prove the above behaviors by reporting extensive image classification results on the CIFAR10, CIFAR100, and Caltech256 datasets.

Generalization Comparison of Deep Neural Networks Via Output Sensitivity

Mahsa Forouzesh, Farnood Salehi, Patrick Thiran

Auto-TLDR; Generalization of Deep Neural Networks using Sensitivity

Abstract Slides Similar

Although recent works have brought some insights into the performance improvement of techniques used in state-of-the-art deep-learning models, more work is needed to understand their generalization properties. We shed light on this matter by linking the loss function to the output's sensitivity to its input. We find a rather strong empirical relation between the output sensitivity and the variance in the bias-variance decomposition of the loss function, which hints on using sensitivity as a metric for comparing the generalization performance of networks, without requiring labeled data. We find that sensitivity is decreased by applying popular methods which improve the generalization performance of the model, such as (1) using a deep network rather than a wide one, (2) adding convolutional layers to baseline classifiers instead of adding fully-connected layers, (3) using batch normalization, dropout and max-pooling, and (4) applying parameter initialization techniques.

Fast and Accurate Real-Time Semantic Segmentation with Dilated Asymmetric Convolutions

Leonel Rosas-Arias, Gibran Benitez-Garcia, Jose Portillo-Portillo, Gabriel Sanchez-Perez, Keiji Yanai

Auto-TLDR; FASSD-Net: Dilated Asymmetric Pyramidal Fusion for Real-Time Semantic Segmentation

Abstract Slides Poster Similar

Recent works have shown promising results applied to real-time semantic segmentation tasks. To maintain fast inference speed, most of the existing networks make use of light decoders, or they simply do not use them at all. This strategy helps to maintain a fast inference speed; however, their accuracy performance is significantly lower in comparison to non-real-time semantic segmentation networks. In this paper, we introduce two key modules aimed to design a high-performance decoder for real-time semantic segmentation for reducing the accuracy gap between real-time and non-real-time segmentation networks. Our first module, Dilated Asymmetric Pyramidal Fusion (DAPF), is designed to substantially increase the receptive field on the top of the last stage of the encoder, obtaining richer contextual features. Our second module, Multi-resolution Dilated Asymmetric (MDA) module, fuses and refines detail and contextual information from multi-scale feature maps coming from early and deeper stages of the network. Both modules exploit contextual information without excessively increasing the computational complexity by using asymmetric convolutions. Our proposed network entitled “FASSD-Net” reaches 78.8% of mIoU accuracy on the Cityscapes validation dataset at 41.1 FPS on full resolution images (1024x2048). Besides, with a light version of our network, we reach 74.1% of mIoU at 133.1 FPS (full resolution) on a single NVIDIA GTX 1080Ti card with no additional acceleration techniques. The source code and pre-trained models are available at https://github.com/GibranBenitez/FASSD-Net.

Resource-efficient DNNs for Keyword Spotting using Neural Architecture Search and Quantization

David Peter, Wolfgang Roth, Franz Pernkopf

Auto-TLDR; Neural Architecture Search for Keyword Spotting in Limited Resource Environments

Abstract Slides Poster Similar

This paper introduces neural architecture search (NAS) for the automatic discovery of small models for keyword spotting (KWS) in limited resource environments. We employ a differentiable NAS approach to optimize the structure of convolutional neural networks (CNNs) to meet certain memory constraints for storing weights as well as constraints on the number of operations per inference. Using NAS only, we were able to obtain a highly efficient model with 95.6% accuracy on the Google speech commands dataset with 494.8 kB of memory usage and 19.6 million operations. Additionally, weight quantization is used to reduce the memory consumption even further. We show that weight quantization to low bit-widths (e.g. 1 bit) can be used without substantial loss in accuracy. By increasing the number of input features from 10 MFCC to 20 MFCC we were able to increase the accuracy to 96.6% at 340.1 kB of memory usage and 27.1 million operations.

Selecting Useful Knowledge from Previous Tasks for Future Learning in a Single Network

Feifei Shi, Peng Wang, Zhongchao Shi, Yong Rui

Auto-TLDR; Continual Learning with Gradient-based Threshold Threshold

Abstract Slides Poster Similar

Continual learning is able to learn new tasks incrementally while avoiding catastrophic forgetting. Recent work has shown that packing multiple tasks into a single network incrementally by iterative pruning and re-training network is a promising method. We build upon this idea and propose an improved version of PackNet, specifically, we propose a novel gradient-based threshold method to reuse the knowledge of the previous tasks selectively when learning new tasks. Our experiments on a variety of classification tasks and different network architectures demonstrate that our method obtains competitive results when compared to PackNet.

Attention As Activation

Yimian Dai, Stefan Oehmcke, Fabian Gieseke, Yiquan Wu, Kobus Barnard

Auto-TLDR; Attentional Activation Units for Convolutional Networks

Abstract Slides Similar

Activation functions and attention mechanisms are typically treated as having different purposes and have evolved differently. However, both concepts can be formulated as a non-linear gating function. Inspired by their similarity, we propose a novel type of activation units called attentional activation~(ATAC) units as a unification of activation functions and attention mechanisms. In particular, we propose a local channel attention module for the simultaneous non-linear activation and element-wise feature refinement, which locally aggregates point-wise cross-channel feature contexts. By replacing the well-known rectified linear units by such ATAC units in convolutional networks, we can construct fully attentional networks that perform significantly better with a modest number of additional parameters. We conducted detailed ablation studies on the ATAC units using several host networks with varying network depths to empirically verify the effectiveness and efficiency of the units. Furthermore, we compared the performance of the ATAC units against existing activation functions as well as other attention mechanisms on the CIFAR-10, CIFAR-100, and ImageNet datasets. Our experimental results show that networks constructed with the proposed ATAC units generally yield performance gains over their competitors given a comparable number of parameters.

NAS-EOD: An End-To-End Neural Architecture Search Method for Efficient Object Detection

Huigang Zhang, Liuan Wang, Jun Sun, Li Sun, Hiromichi Kobashi, Nobutaka Imamura

Auto-TLDR; NAS-EOD: Neural Architecture Search for Object Detection on Edge Devices

Abstract Slides Similar

Model efficiency for object detection has become more and more important recently, especially when intelligent mobile devices are more and more convenient and developed today. Current small models for this task is either extended from the models for classification task, or pruned directly on the basis of large models. These pipelines are not task-specific or data-oriented so that their performance are not good enough for users. In this work, we propose a neural architecture search (NAS) method to build a detection model automatically that can perform well on edge devices. Specifically, the proposed method supports the search of not only multi-scale feature network, but also backbone network. This enables us to search out a global optimal model. To the best of our knowledge, it is a first attempt for searching an overall detection model via NAS. Additionally, we add latency information into the main objective during performance estimation, so that the search process can find a final model suitable for edge devices. Experiments on the PASCAL VOC benchmark indicate that the searched model (named NAS-EOD) can get good accuracy even without ImageNet pre-training. When using ImageNet pre-training, our model is superior to state-of-the-art small object detection models.

FastSal: A Computationally Efficient Network for Visual Saliency Prediction

Feiyan Hu, Kevin Mcguinness

Auto-TLDR; MobileNetV2: A Convolutional Neural Network for Saliency Prediction

Abstract Slides Poster Similar

This paper focuses on the problem of visual saliency prediction, predicting regions of an image that tend to attract human visual attention, under a constrained computational budget. We modify and test various recent efficient convolutional neural network architectures like EfficientNet and MobileNetV2 and compare them with existing state-of-the-art saliency models such as SalGAN and DeepGaze II both in terms of standard accuracy metrics like AUC and NSS, and in terms of the computational complexity and model size. We find that MobileNetV2 makes an excellent backbone for a visual saliency model and can be effective even without a complex decoder. We also show that knowledge transfer from a more computationally expensive model like DeepGaze II can be achieved via pseudo-labelling an unlabelled dataset, and that this approach gives result on-par with many state-of-the-art algorithms with a fraction of the computational cost and model size.

Rethinking of Deep Models Parameters with Respect to Data Distribution

Shitala Prasad, Dongyun Lin, Yiqun Li, Sheng Dong, Zaw Min Oo

Auto-TLDR; A progressive stepwise training strategy for deep neural networks

Abstract Slides Poster Similar

The performance of deep learning models are driven by various parameters but to tune all of them every time, for every dataset, is a heuristic practice. In this paper, unlike the common practice of decaying the learning rate, we propose a step-wise training strategy where the learning rate and the batch size are tuned based on the dataset size. Here, the given dataset size is progressively increased during the training to boost the network performance without saturating the learning curve, after certain epochs. We conducted extensive experiments on multiple networks and datasets to validate the proposed training strategy. The experimental results proves our hypothesis that the learning rate, the batch size and the data size are interrelated and can improve the network accuracy if an optimal progressive stepwise training strategy is applied. The proposed strategy also the overall training computational cost is reduced.

Fine-Tuning DARTS for Image Classification

Muhammad Suhaib Tanveer, Umar Karim Khan, Chong Min Kyung

Auto-TLDR; Fine-Tune Neural Architecture Search using Fixed Operations

Abstract Slides Poster Similar

Neural Architecture Search (NAS) has gained attraction due to superior classification performance. Differential Architecture Search (DARTS) is a computationally light method. To limit computational resources DARTS makes numerous approximations. These approximations result in inferior performance. We propose to fine-tune DARTS using fixed operations as these are independent of these approximations. Our method offers a good trade-off between the number of parameters and classification accuracy. Our approach improves the top-1 accuracy on Fashion-MNIST, CompCars and MIO-TCD datasets by 0.56%, 0.50%, and 0.39%, respectively compared to the state-of-the-art approaches. Our approach performs better than DARTS, improving the accuracy by 0.28%, 1.64%, 0.34%, 4.5%, and 3.27% compared to DARTS, on CIFAR-10, CIFAR-100, Fashion-MNIST, CompCars, and MIO-TCD datasets, respectively.

Operation and Topology Aware Fast Differentiable Architecture Search

Shahid Siddiqui, Christos Kyrkou, Theocharis Theocharides

Auto-TLDR; EDARTS: Efficient Differentiable Architecture Search with Efficient Optimization

Abstract Slides Poster Similar

Differentiable architecture search (DARTS) has gained significant attention amongst neural architecture search approaches due to its effectiveness in finding competitive network architectures with reasonable computational complexity. DARTS' search space however is designed such that even a randomly picked architecture is very competitive and due to the complexity of search architectural building block or cell, it is unclear whether these are certain operations or the cell topology that contributes most to achieving higher final accuracy. In this work, we dissect the DARTS's search space as to understand which components are most effective in producing better architectures. Our experiments show that: (1) Good architectures can be found regardless of the search network depth; (2) Seperable convolution is the most effective operation in the search space; and (3) The cell topology also has substantial effect on the accuracy. Based on these insights, we propose an efficient search approach based referred to as eDARTS, that searches on a pre-specified cell with a good topology with increased attention to important operations using a shallow supernet. Moreover, we propose some optimizations for eDARTS which significantly speed up the search as well as alleviate the well known skip connection aggregation problem of DARTS. eDARTS achieves an error rate of 2.53% on CIFAR-10 using a 3.1M parameters model; while the search cost is less than 30 minutes.

Attention Pyramid Module for Scene Recognition

Zhinan Qiao, Xiaohui Yuan, Chengyuan Zhuang, Abolfazl Meyarian

Auto-TLDR; Attention Pyramid Module for Multi-Scale Scene Recognition

Abstract Slides Poster Similar

The unrestricted open vocabulary and diverse substances of scenery images bring significant challenges to scene recognition. However, most deep learning architectures and attention methods are developed on general-purpose datasets and omit the characteristics of scene data. In this paper, we exploit the attention pyramid module (APM) to tackle the predicament of scene recognition. Our method streamlines the multi-scale scene recognition pipeline, learns comprehensive scene features at various scales and locations, addresses the interdependency among scales, and further assists feature re-calibration as well as aggregation process. APM is extremely light-weighted and can be easily plugged into existing network architectures in a parameter-efficient manner. By simply integrating APM into ResNet-50, we obtain a 3.54\% boost in terms of top-1 accuracy on the benchmark scene dataset. Comprehensive experiments show that APM achieves better performance comparing with state-of-the-art attention methods using significant less computation budget. Code and pre-trained models will be made publicly available.

Efficient Online Subclass Knowledge Distillation for Image Classification

Maria Tzelepi, Nikolaos Passalis, Anastasios Tefas

Auto-TLDR; OSKD: Online Subclass Knowledge Distillation

Abstract Slides Poster Similar

Deploying state-of-the-art deep learning models on embedded systems dictates certain storage and computation limitations. During the recent few years Knowledge Distillation (KD) has been recognized as a prominent approach to address this issue. That is, KD has been effectively proposed for training fast and compact deep learning models by transferring knowledge from more complex and powerful models. However, knowledge distillation, in its conventional form, involves multiple stages of training, rendering it a computationally and memory demanding procedure. In this paper, a novel single-stage self knowledge distillation method is proposed, namely Online Subclass Knowledge Distillation (OSKD), that aims at revealing the similarities inside classes, improving the performance of any deep neural model in an online manner. Hence, as opposed to existing online distillation methods, we are able to acquire further knowledge from the model itself, without building multiple identical models or using multiple models to teach each other, rendering the OSKD approach more efficient. The experimental evaluation on two datasets validates that the proposed method improves the classification performance.

Compression Strategies and Space-Conscious Representations for Deep Neural Networks

Giosuè Marinò, Gregorio Ghidoli, Marco Frasca, Dario Malchiodi

Auto-TLDR; Compression of Large Convolutional Neural Networks by Weight Pruning and Quantization

Abstract Slides Poster Similar

Recent advances in deep learning have made available large, powerful convolutional neural networks (CNN) with state-of-the-art performance in several real-world applications. Unfortunately, these large-sized models have millions of parameters, thus they are not deployable on resource-limited platforms (e.g. where RAM is limited). Compression of CNNs thereby becomes a critical problem to achieve memory-efficient and possibly computationally faster model representations. In this paper, we investigate the impact of lossy compression of CNNs by weight pruning and quantization, and lossless weight matrix representations based on source coding. We tested several combinations of these techniques on four benchmark datasets for classification and regression problems, achieving compression rates up to 165 times, while preserving or improving the model performance.

Contextual Classification Using Self-Supervised Auxiliary Models for Deep Neural Networks

Sebastian Palacio, Philipp Engler, Jörn Hees, Andreas Dengel

Auto-TLDR; Self-Supervised Autogenous Learning for Deep Neural Networks

Abstract Slides Poster Similar

Classification problems solved with deep neural networks (DNNs) typically rely on a closed world paradigm, and optimize over a single objective (e.g., minimization of the cross- entropy loss). This setup dismisses all kinds of supporting signals that can be used to reinforce the existence or absence of particular patterns. The increasing need for models that are interpretable by design makes the inclusion of said contextual signals a crucial necessity. To this end, we introduce the notion of Self-Supervised Autogenous Learning (SSAL). A SSAL objective is realized through one or more additional targets that are derived from the original supervised classification task, following architectural principles found in multi-task learning. SSAL branches impose low-level priors into the optimization process (e.g., grouping). The ability of using SSAL branches during inference, allow models to converge faster, focusing on a richer set of class-relevant features. We equip state-of-the-art DNNs with SSAL objectives and report consistent improvements for all of them on CIFAR100 and Imagenet. We show that SSAL models outperform similar state-of-the-art methods focused on contextual loss functions, auxiliary branches and hierarchical priors.